Share：
Share this content in WeChat
X
[Chinese] [PDF] 9 1
• Review •
Research advances in the integration of multimodal MRI and artificial intelligence for diagnosis and conversion prediction of mild cognitive impairment
LU Bingchuan  HOU Jian 

DOI:10.12015/issn.1674-8034.2025.12.027.


[Abstract] Mild cognitive impairment (MCI) is a critical prodromal stage of Alzheimer's disease (AD), and there is no effective cure currently available for Alzheimer's disease. Consequently, early diagnosis of MCI is crucial for preventing or slowing the progression of AD. The development of multimodal MRI and artificial intelligence (AI) technologies has introduced novel methodologies and perspectives into research on MCI, demonstrating significant potential in the diagnosis of MCI and the prediction of its progression to AD. Nevertheless, several challenges remain in this field, including insufficient standardization of multi-center data and limited generalizability of computational models. This review systematically summarizes recent advances in the integration of multimodal MRI with machine learning and deep learning for MCI classification and AD conversion prediction. Furthermore, it underscores the necessity of establishing unified protocols for multi-center neuroimaging data and developing standardized frameworks for evaluating model robustness. Finally, we propose a promising future direction that integrates multimodal neuroimaging with genetic profiling, with the aim of constructing a more comprehensive biological characterization of MCI and enhancing early intervention strategies.
[Keywords] mild cognitive impairment；Alzheimer's disease；multimodal magnetic resonance imaging；magnetic resonance imaging；machine learning；deep learning

LU Bingchuan1   HOU Jian1, 2*  

1 School of Medical and Life Sciences Chengdu University of Traditional Chinese Medicine, Chengdu 611137, China

2 Department of Radiology, Affiliated Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu 610072, China

Corresponding author: HOU J, E-mail: hoj2000@126.com

Conflicts of interest   None.

Received  2025-08-27
Accepted  2025-11-27
DOI: 10.12015/issn.1674-8034.2025.12.027
DOI:10.12015/issn.1674-8034.2025.12.027.

[1]
YUE J H, ZHANG Q H, YANG X, et al. Magnetic resonance imaging of white matter in Alzheimer's disease: a global bibliometric analysis from 1990 to 2022[J/OL]. Front Neurosci, 2023, 17: 1163809 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/37304017/. DOI: 10.3389/fnins.2023.1163809.
[2]
MIAN M, TAHIRI J, ELDIN R, et al. Overlooked cases of mild cognitive impairment: Implications to early Alzheimer's disease[J/OL]. Ageing Res Rev, 2024, 98: 102335 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/38744405/. DOI: 10.1016/j.arr.2024.102335.
[3]
WANG G, QI J L, LIU X Y, et al. China Alzheimer Report 2024[J]. J Diagn Concepts Pract, 2024, 23(3): 219-256. DOI: 10.16150/j.1671-2870.2024.03.001.
[4]
CONG L, REN Y, WANG Y, et al. Mild cognitive impairment among rural-dwelling older adults in China: A community-based study[J]. Alzheimers Dement, 2023, 19(1): 56-66. DOI: 10.1002/alz.12629.
[5]
SANFORD A M. Mild Cognitive Impairment[J]. Clin Geriatr Med, 2017, 33(3): 325-337. DOI: 10.1016/j.cger.2017.02.005.
[6]
SHIGEMIZU D, AKIYAMA S, HIGAKI S, et al. Prognosis prediction model for conversion from mild cognitive impairment to Alzheimer's disease created by integrative analysis of multi-omics data[J/OL]. Alzheimers Res Ther, 2020, 12(1): 145 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/33172501/. DOI: 10.1186/s13195-020-00716-0.
[7]
HAN S W, LI X L, WANG Y, et al. Progress in multimodal MRI research on acupuncture at Siguan point for the treatment of mild cognitive impairment[J]. Chin J Magn Reson Imaging, 2024, 15(6): 138-143. DOI: 10.12015/issn.1674-8034.2024.06.021.
[8]
CHEN Z, CHEN K, LI Y, et al. Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer's disease: Inter-cohort validation of Shanghai Memory Study and ADNI[J/OL]. Hum Brain Mapp, 2024, 45(1): e26529 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/37991144/. DOI: 10.1002/hbm.26529.
[9]
WANG L X, WANG Y Z, HAN C G, et al. Revolutionizing early Alzheimer's disease and mild cognitive impairment diagnosis: a deep learning MRI meta-analysis[J]. Arq Neuropsiquiatr, 2024, 82(8): 1-10. DOI: 10.1055/s-0044-1788657.
[10]
ZAMANI J, SADR A, JAVADI A H. Diagnosis of early mild cognitive impairment using a multiobjective optimization algorithm based on T1-MRI data[J/OL]. Sci Rep, 2022, 12(1): 1020 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/35046444/. DOI: 10.1038/s41598-022-04943-3.
[11]
RAO G, GAO H, WANG X, et al. MRI measurements of brain hippocampus volume in relation to mild cognitive impairment and Alzheimer disease: A systematic review and meta-analysis[J/OL]. Medicine (Baltimore), 2023, 102(36): e34997 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/37682140/. DOI: 10.1097/md.0000000000034997.
[12]
ALYOUBI E H, MORIA K M, ALGHAMDI J S, et al. An Optimized Deep Learning Model for Predicting Mild Cognitive Impairment Using Structural MRI[J/OL]. Sensors (Basel), 2023, 23(12): 5648 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/37420812/. DOI: 10.3390/s23125648.
[13]
UMEMURA Y, WATANABE K, KASAI S, et al. Choroid plexus enlargement in mild cognitive impairment on MRI: a large cohort study[J]. Eur Radiol, 2024, 34(8): 5297-5304. DOI: 10.1007/s00330-023-10572-9.
[14]
JAO C W, WU Y T, YEH J H, et al. Exploring cortical morphology biomarkers of amnesic mild cognitive impairment using novel fractal dimension-based structural MRI analysis[J]. Eur J Neurosci, 2024, 60(9): 6254-6266. DOI: 10.1111/ejn.16557.
[15]
MA Z, JING B, LI Y, et al. Identifying Mild Cognitive Impairment with Random Forest by Integrating Multiple MRI Morphological Metrics[J]. J Alzheimers Dis, 2020, 73(3): 991-1002. DOI: 10.3233/jad-190715.
[16]
LIN A, CHEN Y, CHEN Y, et al. MRI radiomics combined with machine learning for diagnosing mild cognitive impairment: a focus on the cerebellar gray and white matter[J/OL]. Front Aging Neurosci, 2024, 16: 1460293 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/39430972/. DOI: 10.3389/fnagi.2024.1460293.
[17]
WEI X, WANG L, YU F, et al. Identifying the neural marker of chronic sciatica using multimodal neuroimaging and machine learning analyses[J/OL]. Front Neurosci, 2022, 16: 1036487 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/36532276/. DOI: 10.3389/fnins.2022.1036487.
[18]
WU Y Q, WANG Y N, ZHANG L J, et al. Regional Homogeneity in Patients With Mild Cognitive Impairment: A Resting-State Functional Magnetic Resonance Imaging Study[J/OL]. Front Aging Neurosci, 2022, 14: 877281 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/35493938/. DOI: 10.3389/fnagi.2022.877281.
[19]
IBRAHIM B, SUPPIAH S, IBRAHIM N, et al. Diagnostic power of resting-state fMRI for detection of network connectivity in Alzheimer's disease and mild cognitive impairment: A systematic review[J]. Hum Brain Mapp, 2021, 42(9): 2941-2968. DOI: 10.1002/hbm.25369.
[20]
WANG Y, LI Q, YAO L, et al. Shared and differing functional connectivity abnormalities of the default mode network in mild cognitive impairment and Alzheimer's disease[J/OL]. Cereb Cortex, 2024, 34(3): bhae094 [2025-11-04]. https://pubmed.ncbi.nlm.nih.gov/38521993/. DOI: 10.1093/cercor/bhae094.
[21]
XU W, CHEN S, XUE C, et al. Functional MRI-Specific Alterations in Executive Control Network in Mild Cognitive Impairment: An ALE Meta-Analysis[J/OL]. Front Aging Neurosci, 2020, 12: 578863 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/33192472/. DOI: 10.3389/fnagi.2020.578863.
[22]
LIU W, LIU L, CHENG X, et al. Functional Integrity of Executive Control Network Contributed to Retained Executive Abilities in Mild Cognitive Impairment[J/OL]. Front Aging Neurosci, 2021, 13: 710172 [2025-11-04]. https://pubmed.ncbi.nlm.nih.gov/34899264/. DOI: 10.3389/fnagi.2021.710172.
[23]
MENON V. Large-scale brain networks and psychopathology: a unifying triple network model[J]. Trends Cogn Sci, 2011, 15(10): 483-506. DOI: 10.1016/j.tics.2011.08.003.
[24]
SONG Y, XU W, CHEN S, et al. Functional MRI-Specific Alterations in Salience Network in Mild Cognitive Impairment: An ALE Meta-Analysis[J/OL]. Front Aging Neurosci, 2021, 13: 695210 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/34381352/. DOI: 10.3389/fnagi.2021.695210.
[25]
PAN C, LI R, YUAN X, et al. Neural network disruptions between default mode network and salience network in mild cognitive impairment with neuropsychiatric symptoms[J/OL]. Int Psychogeriatr, 2025: 100092 [2025-11-04]. https://pubmed.ncbi.nlm.nih.gov/40413109/. DOI: 10.1016/j.inpsyc.2025.100092.
[26]
LIN A L, LAIRD A R, FOX P T, et al. Multimodal MRI neuroimaging biomarkers for cognitive normal adults, amnestic mild cognitive impairment, and Alzheimer's disease[J/OL]. Neurol Res Int, 2012, 2012: 907409 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/21949904/. DOI: 10.1155/2012/907409.
[27]
KNUDSEN L V, GAZERANI P, DUAN Y, et al. The role of multimodal MRI in mild cognitive impairment and Alzheimer's disease[J]. J Neuroimaging, 2022, 32(1): 148-157. DOI: 10.1111/jon.12940.
[28]
JITSUISHI T, YAMAGUCHI A. Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data[J/OL]. Sci Rep, 2022, 12(1): 4284 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/35277565/. DOI: 10.1038/s41598-022-08231-y.
[29]
KANG L, JIANG J, HUANG J, et al. Identifying Early Mild Cognitive Impairment by Multi-Modality MRI-Based Deep Learning[J/OL]. Front Aging Neurosci, 2020, 12: 206 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/33101003/. DOI: 10.3389/fnagi.2020.00206.
[30]
SOMAN S, RAGHAVAN S, RAJESH P G, et al. Relationship between Cerebral Perfusion on Arterial Spin Labeling (ASL) MRI with Brain Volumetry and Cognitive Performance in Mild Cognitive Impairment and Dementia due to Alzheimer's Disease[J]. Ann Indian Acad Neurol, 2021, 24(4): 559-565. DOI: 10.4103/aian.AIAN_848_20.
[31]
ZHU D, FU X, LIU J, et al. Multiparametric Chemical Exchange Saturation Transfer MRI Detects Metabolic Changes in Mild Cognitive Impairment Cases at 3.0 Tesla[J/OL]. Neurochem Res, 2024, 50(1): 51 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/39648256/. DOI: 10.1007/s11064-024-04307-5.
[32]
GUO Z, JIANG Y, QIN X, et al. Amide Proton Transfer-Weighted MRI Might Help Distinguish Amnestic Mild Cognitive Impairment From a Normal Elderly Population[J/OL]. Front Neurol, 2021, 12: 707030 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/34712196/. DOI: 10.3389/fneur.2021.707030.
[33]
WANG D, WANG X N, GAO P, et al. Application of Amide Proton Transfer Magnetic Resonance Imaging in Alzheimer's Disease and Mild Cognitive Impairment[J]. Chin J Med Imaging, 2022, 30(5): 430-434. DOI: 10.3969/j.issn.1005-5185.2022.05.003.
[34]
ZHAO L, TENG J, MAI W, et al. A Pilot Study on the Cutoff Value of Related Brain Metabolite in Chinese Elderly Patients With Mild Cognitive Impairment Using MRS[J/OL]. Front Aging Neurosci, 2021, 13: 617611 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/33897404/. DOI: 10.3389/fnagi.2021.617611.
[35]
PIERSSON A D, IBRAHIM B, SUPPIAH S, et al. Multiparametric MRI for the improved diagnostic accuracy of Alzheimer's disease and mild cognitive impairment: Research protocol of a case-control study design[J/OL]. PLoS One, 2021, 16(9): e0252883 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/34547018/. DOI: 10.1371/journal.pone.0252883.
[36]
HWANG H, KIM S E, LEE H J, et al. Identification of amnestic mild cognitive impairment by structural and functional MRI using a machine-learning approach[J/OL]. Clin Neurol Neurosurg, 2024, 238: 108177 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/38402707/. DOI: 10.1016/j.clineuro.2024.108177.
[37]
WANG L, FENG Q, GE X, et al. Textural features reflecting local activity of the hippocampus improve the diagnosis of Alzheimer's disease and amnestic mild cognitive impairment: A radiomics study based on functional magnetic resonance imaging[J/OL]. Front Neurosci, 2022, 16: 970245 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/36003964/. DOI: 10.3389/fnins.2022.970245.
[38]
XIE Y, CUI Z, ZHANG Z, et al. Identification of Amnestic Mild Cognitive Impairment Using Multi-Modal Brain Features: A Combined Structural MRI and Diffusion Tensor Imaging Study[J]. J Alzheimers Dis, 2015, 47(2): 509-522. DOI: 10.3233/jad-150184.
[39]
NELSON M R, KEELING E G, STOKES A M, et al. Exploring white matter microstructural alterations in mild cognitive impairment: a multimodal diffusion MRI investigation utilizing diffusion kurtosis and free-water imaging[J/OL]. Front Neurosci, 2024, 18: 1440653 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/39170682/. DOI: 10.3389/fnins.2024.1440653.
[40]
SUI H, YANG J, XIANG H, et al. Combining ADC values in DWI with rCBF values in arterial spin labeling (ASL) for the diagnosis of mild cognitive impairment (MCI)[J/OL]. Medicine (Baltimore), 2023, 102(37): e34979 [2025-09-01].https://pubmed.ncbi.nlm.nih.gov/37713879/. DOI: 10.1097/md.0000000000034979.
[41]
BAPAT R, MA D, DUONG T Q. Predicting Four-Year's Alzheimer's Disease Onset Using Longitudinal Neurocognitive Tests and MRI Data Using Explainable Deep Convolutional Neural Networks[J]. J Alzheimers Dis, 2024, 97(1): 459-469. DOI: 10.3233/jad-230893.
[42]
AI M, LIU Y, LIU D, et al. Research progress in predicting the conversion from mild cognitive impairment to Alzheimer's disease via multimodal MRI and artificial intelligence[J/OL]. Front Neurol, 2025, 16: 1596632 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/40529431/. DOI: 10.3389/fneur.2025.1596632.
[43]
COLLINS G S, DHIMAN P, ANDAUR NAVARRO C L, et al. Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence[J/OL]. BMJ Open, 2021, 11(7): e048008 [2025-11-04]. https://pubmed.ncbi.nlm.nih.gov/38521993/. DOI: 10.1136/bmjopen-2020-048008.
[44]
LIU X, CRUZ RIVERA S, MOHER D, et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension[J]. Lancet Digit Health, 2020, 2(10): e537-e548. DOI: 10.1016/s2589-7500(20)30218-1.
[45]
WANG R, CHEN S, ZHAO C L, et al. Prognostic study of mild cognitive impairment progressing to Alzheimer's disease based on polygenic risk score and machine learning modeling strategy[J]. Chin J Dis Control Prev, 2023, 27(6): 684-690. DOI: 10.16462/j.cnki.zhjbkz.2023.06.012.
[46]
VECCHIO D, PIRAS F, NATALIZI F, et al. Evaluating conversion from mild cognitive impairment to Alzheimer's disease with structural MRI: a machine learning study[J/OL]. Brain Commun, 2025, 7(1): fcaf027 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/39886067/. DOI: 10.1093/braincomms/fcaf027.
[47]
FICIARÀ E, CRESPI V, GADEWAR S P, et al. Predicting Progression from Mild Cognitive Impairment to Alzheimer's Disease using MRI-based Cortical Features and a Two-State Markov Model[J]. Proc IEEE Int Symp Biomed Imaging, 2021, 2021: 1145-1149. DOI: 10.1109/isbi48211.2021.9434143.
[48]
CHEN J, YANG J, SHEN D, et al. A Predictive Model of the Progression to Alzheimer's Disease in Patients with Mild Cognitive Impairment Based on the MRI Enlarged Perivascular Spaces[J]. J Alzheimers Dis, 2024, 101(1): 159-173. DOI: 10.3233/jad-240523.
[49]
CIRINCIONE A, LYNCH K, BENNETT J, et al. Prediction of future dementia among patients with mild cognitive impairment (MCI) by integrating multimodal clinical data[J/OL]. Heliyon, 2024, 10(17): e36728 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/39281465/. DOI: 10.1016/j.heliyon.2024.e36728.
[50]
JO T, NHO K, SAYKIN A J. Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data[J/OL]. Front Aging Neurosci, 2019, 11: 220 [2025-06-26]. https://pubmed.ncbi.nlm.nih.gov/31481890/. DOI: 10.3389/fnagi.2019.00220.
[51]
WU X H, JIANG L, ZHU J R, et al. Deep learning for diagnosis of mild cognitive impairment in older adults:a scoping review[J]. Chin J Rehabil Theory Pract, 2025, 31(6): 674-681. DOI: 10.3969/j.issn.1006-9771.2025.06.008.
[52]
LIAN C, LIU M, PAN Y, et al. Attention-Guided Hybrid Network for Dementia Diagnosis With Structural MR Images[J]. IEEE Trans Cybern, 2022, 52(4): 1992-2003. DOI: 10.1109/tcyb.2020.3005859.
[53]
LIN W, TONG T, GAO Q, et al. Convolutional Neural Networks-Based MRI Image Analysis for the Alzheimer's Disease Prediction From Mild Cognitive Impairment[J/OL]. Front Neurosci, 2018, 12: 777 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/30455622/. DOI: 10.3389/fnins.2018.00777.
[54]
OCASIO E, DUONG T Q. Deep learning prediction of mild cognitive impairment conversion to Alzheimer's disease at 3 years after diagnosis using longitudinal and whole-brain 3D MRI[J/OL]. PeerJ Comput Sci, 2021, 7: e560 [2025-08-26]. https://pubmed.ncbi.nlm.nih.gov/34141888/. DOI: 10.7717/peerj-cs.560.
[55]
HOANG G M, KIM U H, KIM J G. Vision transformers for the prediction of mild cognitive impairment to Alzheimer's disease progression using mid-sagittal sMRI[J/OL]. Front Aging Neurosci, 2023, 15: 1102869 [2025-09-01]. https://pubmed.ncbi.nlm.nih.gov/37122374/. DOI: 10.3389/fnagi.2023.1102869.
[56]
WU Y, YIN J, YANG B, et al. Association Analysis of Polymorphisms in BIN1, MC1R, STARD6 and PVRL2 with Mild Cognitive Impairment in Elderly Carrying APOE ε4 Allele[J]. Neuropsychiatr Dis Treat, 2021, 17: 1125-1133. DOI: 10.2147/ndt.S296144.

PREV Progress in research on central mechanisms of rs-fMRI in acupuncture treatment of Alzheimer<sup><sup>,</sup></sup>s disease
NEXT Research progress on evaluating glymphatic system function in sleep disorder patients based on DTI-ALPS
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn